• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.856-868
• /
• 2007

We propose an effective method for block classification in a document image. The gray level document image is converted to the binary image for a block segmentation. This binary image would be smoothed to find the locations and sizes of each block. And especially during this smoothing, the inner block heights of each block are obtained. The gray level image is divided to several blocks by these location informations. The SGLDM(spatial gray level dependence matrices) are made using the each gray-level document block and the seven second-order statistical texture features are extracted from the (0,1) direction's SGLDM which include the document attributes. Document image blocks are classified to two groups, text and non-text group, by the inner block height of the block at the nearest neighbor rule. The seven texture features(that were extracted from the SGLDM) are used for the five detail categories of small font, large font, table, graphic and photo blocks. These document blocks are available not only for structure analysis of document recognition but also the various applied area.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.275-278
• /
• 2020

In this paper, we proposed a deep learning based character recognition system through virtual data generation. In order to secure the learning data that takes the largest weight in supervised learning, virtual data was created. Also, after creating virtual data, data generalization was performed to cope with various data by using augmentation parameter. Finally, the learning data composition generated data by assigning various values to augmentation parameter and font parameter. Test data for measuring the character recognition performance was constructed by cropping the text area from the actual image data. The test data was augmented considering the image distortion that may occur in real environment. Deep learning algorithm uses YOLO v3 which performs detection in real time. Inference result outputs the final detection result through post-processing.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.425-428
• /
• 2001

본 논문에서는 문서 위의 문자를 Off-Line방식으로 컴퓨터에 저장할 수 있도록 기하학적 패턴 벡터를 이용하여 한·영문자 및 글꼴을 인식하는 알고리즘을 제안하였다. 일반적으로 문서에서는 여러 가지 글꼴에 따라 글자의 형태가 다르므로 대표적인 한·영 세 가지 글꼴을 기하학적 패턴(Geometrical Pattern Vector)을 이용하여 크기와 이동에 인식하도록 하였다. 이진 입력 한영혼용 영상에서 잡음을 제거하고 수평·수직 투영 기법을 이용하여 한 문자를 분할하여 문자의 폭에 따라 기하학적 패턴을 추출한다. 추출한 패턴은 각 합계를 계산하여 기준 패턴 합계와 비교한 후 기준 패턴 문자와 글꼴을 인식하게 된다. 마지막으로 제안한 알고리즘의 성능을 평가하기 위해 크기, 이동 변형이 있는 대표적인 한·영 글꼴(신명조, 궁서, 고딕)체와 영어 Time New Roman체를 대상으로 모의 실험을 수행하였다. 제안한 알고리즘은 기존의 원형 패턴 알고리즘보다 문자인식률과 글꼴 그리고 영어의 대·소문자를 구별하는 우수함을 보였다.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.194-199
• /
• 1997

본 논문에서는 글꼴의 변화와 잡영을 흡수할 수 있도록 자소의 탐색 영역을 정의 하였으며 이 영역에 나타나는 횡모음과 종모음의 주획을 추출하는 방법을 기술하였다. 종모음 영역에서 추출한 수직획들과 횡모음 영역에서 추출한 수평획들을 각각 종모음과 횡모음의 주획이 될 수 있는 후보들로써 이들로 부터 종모음과 횡모음의 존재를 파악하는 것이 한글 유형 분류의 주된 내용이다. 그러나 다양한 글꼴에 나타나는 수평획들로부터 곧바로 횡모음의 존재를 파악하는 것은 쉬운 문제가 아니다 본 논문에서는 기존의 트리 분류기를 확장하여 복잡하고 다양한 특징을 단계별로 단순화시키고 트리 분류기의 상위 노드에서 결정된 정보와 제약 조건을 이용하여 유형을 분류하는 방법을 제안하였다. 제안된 방법은 한글 상위 빈도 1405자, 3가지 글꼴에 대하여 99.8 %의 유형 분류율을 보이고 있다.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.916-919
• /
• 2002

This paper introduces the problem of typeface classification of Hangul characters and proposes features for typeface classification among Serif and Sans-serif classes. Serif classes have a small decorative stroke around the beginning of vertical strokes, while Sans-serif classes have no serif. Therefore, the serif part is first segmented from the vertical strokes, and the direction of the serif is computed as the feature for Hangul typeface identification. To evaluate the performance of the proposed system, we used 3,000 characters extracted from Korean documents - 1,500 from Serif fonts, other 1,500 from Sans-serif fonts.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.5
• /
• pp.43-51
• /
• 1993

A new Hangul code called Truecode is developed for accomodating to the future computing environments of graphical user interface and multimedia as well as for corresponding with the invention principle of Hangul. Truecode is not a forced two-byte code of syllable unit, as completion-type of combination-type, currently used, but a one byte code of phoneme unit, which can represent initial consonant, vowel, and final consonant each. It is quite different from three-byte code of syllable unit and also does not require the fill code used for three-byte code. We expect great contribution to the Hangul culture from Truecode's some important following features. It can express all the Korean characters we may imagine and does not cause any problem in communication. As well as we may use direct connection font, we can assign ont-to-one correspondence between Truecode and a keyboard with three sets. Truecode has a good advantage in developing application softwares of Hangul and it can nicely be applied to the fields of speech recognition and artificial intelligence using natural language.

• Annual Conference on Human and Language Technology
• /
• 1990.11a
• /
• pp.183-190
• /
• 1990

본 논문에서는 인쇄체 한글문자를 실용적으로 인식하기 위하여 고안된 계층적 신경망을 소개하고, 이를 다중활자체의 한글문자를 인식하는 문제에 적용하였다. 이 신경망은 입력된 문자영상을 6가지의 유형으로 분류한 후, 해당 유형을 처리하는 신경망에서 실제 문자를 인식하도록 구성되었다. 또한 각 신경망을 모든 입력영상의 모든 출력노드에 대해 고르게 학습시키기 위하여 Backpropagation 알고리즘을 개선한 Descending Epsilon 알고리즘을 도입하였다. 그 결과 사용빈도수가 높은 한글 520자에 대해 94.4 - 98.4%의 인식률을 얻음으로써 본 논문에서 제안한 시스템이 다양한 활자체로 이루어진 실제 문서인식시스템의 문자인식부에 효과적으로 사용될 수 있음을 제시하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.718-721
• /
• 2023

이미지 내 글꼴을 파악하는 것은 디자인 자료 제작, 저작권 확인 등 다양한 곳에서 중요한 문제이다. 하지만 이미지 내 한글 글꼴을 자동으로 식별하는 시스템은 아직 존재하지 않으며, 수동으로 한글 글꼴을 파악하는 것은 시간과 정확도 측면에서 매우 비효율적이다. 따라서 본 논문에서는 이미지 내 한글 글꼴을 자동으로 인식하는 시스템을 개발한다. 본 논문에서 개발한 시스템은 크게 두 가지 기법을 사용한다: (1) 한글의 기하학적인 특성을 활용하여 글자 단위로 텍스트를 인식하며, (2) 단어가 아닌 글자 단위로 글꼴을 분류하고 각 글자에 대한 글꼴 분류 결과를 종합하여 최종적인 글꼴 분류 결과를 얻는다. 10가지 한글 글꼴이 나타나는 직접 제작한 이미지를 사용하여 시스템의 성능을 평가한 결과 제안 방법은 비교 방법에 비해 더욱 정확히 한글 글꼴을 분류함을 확인하였다.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.443-450
• /
• 2003

In this paper, we proposed the novel hierarchical algorithm for the recognition of English calling cards that processes multiresolution images of calling cards hierarchically to extract individual characters and recognizes the extracted characters by using the enhanced neural network method. The hierarchical recognition algorithm generates multiresolution images of calling cards, and each processing step in the algorithm selects and processes the image with suitable resolution for lower processing overhead and improved output. That is, first, the image of 1/3 times resolution, to which the horizontal smearing method is applied, is used to extract the areas including only characters from the calling card image, and next, by applying the vertical smearing and the contour tracking masking, the image of a half time resolution is used to extract individual characters from the character string areas. Lastly, the original image is used in the recognition step, because the image includes the morphological information of characters accurately. And for the recognition of characters with diverse font types and various sizes, the enhanced RBF network that improves the middle layer based on the ART1 was proposed and applied. The results of experiments on a large number of calling card images showed that the proposed algorithm is greatly improved in the performance of character extraction and recognition compared with the traditional recognition algorithms.